• International Journal of Advanced Culture Technology
• /
• v.5 no.1
• /
• pp.83-89
• /
• 2017

In this paper, we propose an extended method of one-hot Long Short-Term Memory (LSTM) and evaluate the performance on spam filtering task. Most of traditional methods proposed for spam filtering task use word occurrences to represent spam or non-spam messages and all syntactic and semantic information are ignored. Major issue appears when both spam and non-spam messages share many common words and noise words. Therefore, it becomes challenging to the system to filter correct labels between spam and non-spam. Unlike previous studies on information filtering task, instead of using only word occurrence and word context as in probabilistic models, we apply a neural network-based approach to train the system filter for a better performance. In addition to one-hot representation, using term weight with attention mechanism allows classifier to focus on potential words which most likely appear in spam and non-spam collection. As a result, we obtained some improvement over the performances of the previous methods. We find out using region embedding and pooling features on the top of LSTM along with attention mechanism allows system to explore a better document representation for filtering task in general.

• Food Science and Industry
• /
• v.54 no.3
• /
• pp.160-170
• /
• 2021

A recent advance in communication technologies accelerates the spread of food safety issues once presented by the news media. To respond to those safety issues and take steps in a timely manner, automatically detecting related information from the news data matters. This work presents an AI-based system that detects risk information within a food-related news article. Experts in food safety areas participated in labeling risk information from the food-related news articles; we acquired 43,527 articles in which food names and risk information are marked as labels. Based on the news document, our system automatically detects food names and risk information by analyzing similarities between words within a text by leveraging learned word embedding vectors. Our AI-based system shows higher detection accuracy scores over a non-AI rule-based system: achieving an absolute gain of +32.94% in F1 for the food name category and +41.53% for the risk information category.

• Asia pacific journal of information systems
• /
• v.8 no.2
• /
• pp.53-67
• /
• 1998

The explosive growth of the Web is providing end-users access to ever-increasing volumes of information. The resources of legacy systems and relational databases have also been made available to the Web browser, which has become an essential business tool. Recently, model management on the Internet/Web is also proposed with its conceptual design or prototypical system like DecisionNet and DSS Web. However, they are also suffering from the same symptoms as the Web, Although we can identify the elements of a page with HTML tags and (declare) the relationships among the various document elements, they are semantically opaque to computer systems and have no domain-specific meaning. However, HTML is not extensible, so developers are forced to invent convoluted, non-standard solutions for embedding and parsing data. Extensible Markup Language (XML) is a simplified subset of SGML that has many benefits for folks who want to improve structure, maintainability, searchability, presentation, and other aspects of their document management. This paper proposes a structured markup language for model representation and management on the Web as an XML application. The language is based on a conceptual modeling framework, Object-Oriented Structured Modeling (OOSM), which is an extension of the structured modeling.

• Smart Media Journal
• /
• v.11 no.10
• /
• pp.89-96
• /
• 2022

An open domain machine reading comprehension is a model that adds a function to search paragraphs as there are no paragraphs related to a given question. Document searches have an issue of lower performance with a lot of documents despite abundant research with word frequency based TF-IDF. Paragraph selections also have an issue of not extracting paragraph contexts, including sentence characteristics accurately despite a lot of research with word-based embedding. Document reading comprehension has an issue of slow learning due to the growing number of parameters despite a lot of research on BERT. Trying to solve these three issues, this study used BM25 which considered even sentence length and InferSent to get sentence contexts, and proposed an open domain machine reading comprehension with ALBERT to reduce the number of parameters. An experiment was conducted with SQuAD1.1 datasets. BM25 recorded a higher performance of document research than TF-IDF by 3.2%. InferSent showed a higher performance in paragraph selection than Transformer by 0.9%. Finally, as the number of paragraphs increased in document comprehension, ALBERT was 0.4% higher in EM and 0.2% higher in F1.

• Journal of Intelligence and Information Systems
• /
• v.28 no.2
• /
• pp.127-146
• /
• 2022

Recently, as word embedding has shown excellent performance in various tasks of deep learning-based natural language processing, researches on the advancement and application of word, sentence, and document embedding are being actively conducted. Among them, cross-language transfer, which enables semantic exchange between different languages, is growing simultaneously with the development of embedding models. Academia's interests in vector alignment are growing with the expectation that it can be applied to various embedding-based analysis. In particular, vector alignment is expected to be applied to mapping between specialized domains and generalized domains. In other words, it is expected that it will be possible to map the vocabulary of specialized fields such as R&D, medicine, and law into the space of the pre-trained language model learned with huge volume of general-purpose documents, or provide a clue for mapping vocabulary between mutually different specialized fields. However, since linear-based vector alignment which has been mainly studied in academia basically assumes statistical linearity, it tends to simplify the vector space. This essentially assumes that different types of vector spaces are geometrically similar, which yields a limitation that it causes inevitable distortion in the alignment process. To overcome this limitation, we propose a deep learning-based vector alignment methodology that effectively learns the nonlinearity of data. The proposed methodology consists of sequential learning of a skip-connected autoencoder and a regression model to align the specialized word embedding expressed in each space to the general embedding space. Finally, through the inference of the two trained models, the specialized vocabulary can be aligned in the general space. To verify the performance of the proposed methodology, an experiment was performed on a total of 77,578 documents in the field of 'health care' among national R&D tasks performed from 2011 to 2020. As a result, it was confirmed that the proposed methodology showed superior performance in terms of cosine similarity compared to the existing linear vector alignment.

• 한국어정보학회:학술대회논문집
• /
• 2017.10a
• /
• pp.194-196
• /
• 2017

기존의 단어 기반 접근법을 이용한 개체 연결은 단어의 변형, 신조어 등이 빈번하게 나타나는 비정형 문장에 대해서는 좋은 성능을 기대하기 어렵다. 본 논문에서는 문서 임베딩과 선형 변환을 이용하여 단어 기반 접근법의 단점을 해소하는 개체 연결을 제안한다. 문서 임베딩은 하나의 문서 전체를 벡터 공간에 표현하여 문서 간 의미적 유사도를 계산할 수 있다. 본 논문에서는 또한 비교적 정형 문장인 위키백과 문장과 비정형 문장인 소셜 미디어 문장 사이에 선형 변환을 수행하여 두 문형 사이의 표현 격차를 해소하였다. 제안하는 개체 연결 방법은 대표적인 소셜 미디어인 트위터 환경 문장에서 단어 기반 접근법과 비교하여 높은 성능 향상을 보였다.

• Journal of Intelligence and Information Systems
• /
• v.25 no.3
• /
• pp.161-177
• /
• 2019

In this paper, we study the performance improvement of the answer extraction in Question-Answering system by using sentence dependency parsing result. The Question-Answering (QA) system consists of query analysis, which is a method of analyzing the user's query, and answer extraction, which is a method to extract appropriate answers in the document. And various studies have been conducted on two methods. In order to improve the performance of answer extraction, it is necessary to accurately reflect the grammatical information of sentences. In Korean, because word order structure is free and omission of sentence components is frequent, dependency parsing is a good way to analyze Korean syntax. Therefore, in this study, we improved the performance of the answer extraction by adding the features generated by dependency parsing analysis to the inputs of the answer extraction model (Bidirectional LSTM-CRF). The process of generating the dependency graph embedding consists of the steps of generating the dependency graph from the dependency parsing result and learning the embedding of the graph. In this study, we compared the performance of the answer extraction model when inputting basic word features generated without the dependency parsing and the performance of the model when inputting the addition of the Eojeol tag feature and dependency graph embedding feature. Since dependency parsing is performed on a basic unit of an Eojeol, which is a component of sentences separated by a space, the tag information of the Eojeol can be obtained as a result of the dependency parsing. The Eojeol tag feature means the tag information of the Eojeol. The process of generating the dependency graph embedding consists of the steps of generating the dependency graph from the dependency parsing result and learning the embedding of the graph. From the dependency parsing result, a graph is generated from the Eojeol to the node, the dependency between the Eojeol to the edge, and the Eojeol tag to the node label. In this process, an undirected graph is generated or a directed graph is generated according to whether or not the dependency relation direction is considered. To obtain the embedding of the graph, we used Graph2Vec, which is a method of finding the embedding of the graph by the subgraphs constituting a graph. We can specify the maximum path length between nodes in the process of finding subgraphs of a graph. If the maximum path length between nodes is 1, graph embedding is generated only by direct dependency between Eojeol, and graph embedding is generated including indirect dependencies as the maximum path length between nodes becomes larger. In the experiment, the maximum path length between nodes is adjusted differently from 1 to 3 depending on whether direction of dependency is considered or not, and the performance of answer extraction is measured. Experimental results show that both Eojeol tag feature and dependency graph embedding feature improve the performance of answer extraction. In particular, considering the direction of the dependency relation and extracting the dependency graph generated with the maximum path length of 1 in the subgraph extraction process in Graph2Vec as the input of the model, the highest answer extraction performance was shown. As a result of these experiments, we concluded that it is better to take into account the direction of dependence and to consider only the direct connection rather than the indirect dependence between the words. The significance of this study is as follows. First, we improved the performance of answer extraction by adding features using dependency parsing results, taking into account the characteristics of Korean, which is free of word order structure and omission of sentence components. Second, we generated feature of dependency parsing result by learning - based graph embedding method without defining the pattern of dependency between Eojeol. Future research directions are as follows. In this study, the features generated as a result of the dependency parsing are applied only to the answer extraction model in order to grasp the meaning. However, in the future, if the performance is confirmed by applying the features to various natural language processing models such as sentiment analysis or name entity recognition, the validity of the features can be verified more accurately.

• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.267-286
• /
• 2023

The conversational agents such as AI speakers utilize voice conversation for human-computer interaction. Voice recognition errors often occur in conversational situations. Recognition errors in user utterance records can be categorized into two types. The first type is misrecognition errors, where the agent fails to recognize the user's speech entirely. The second type is misinterpretation errors, where the user's speech is recognized and services are provided, but the interpretation differs from the user's intention. Among these, misinterpretation errors require separate error detection as they are recorded as successful service interactions. In this study, various text separation methods were applied to detect misinterpretation. For each of these text separation methods, the similarity of consecutive speech pairs using word embedding and document embedding techniques, which convert words and documents into vectors. This approach goes beyond simple word-based similarity calculation to explore a new method for detecting misinterpretation errors. The research method involved utilizing real user utterance records to train and develop a detection model by applying patterns of misinterpretation error causes. The results revealed that the most significant analysis result was obtained through initial consonant extraction for detecting misinterpretation errors caused by the use of unregistered neologisms. Through comparison with other separation methods, different error types could be observed. This study has two main implications. First, for misinterpretation errors that are difficult to detect due to lack of recognition, the study proposed diverse text separation methods and found a novel method that improved performance remarkably. Second, if this is applied to conversational agents or voice recognition services requiring neologism detection, patterns of errors occurring from the voice recognition stage can be specified. The study proposed and verified that even if not categorized as errors, services can be provided according to user-desired results.

• Journal of the Korean Society for Library and Information Science
• /
• v.53 no.2
• /
• pp.179-199
• /
• 2019

In this paper, we propose optimal methodologies for classifying patent literature by examining various feature extraction methods, machine learning and deep learning models, and provide optimal performance through experiments. We compared the traditional BoW method and a distributed representation method (word embedding vector) as a feature extraction, and compared the morphological analysis and multi gram as the method of constructing the document collection. In addition, classification performance was verified using traditional machine learning model and deep learning model. Experimental results show that the best performance is achieved when we apply the deep learning model with distributed representation and morphological analysis based feature extraction. In Section, Class and Subclass classification experiments, We improved the performance by 5.71%, 18.84% and 21.53%, respectively, compared with traditional classification methods.

• Journal of KIISE
• /
• v.43 no.8
• /
• pp.902-909
• /
• 2016

Question answering system (QA system) is a system that finds an actual answer to the question posed by a user, whereas a typical search engine would only find the links to the relevant documents. Recent works related to the open domain QA systems are receiving much attention in the fields of natural language processing, artificial intelligence, and data mining. However, the prior works on QA systems simply replace all words that are not in the training data with a single token, even though such unseen words are likely to play crucial roles in differentiating the candidate answers from the actual answers. In this paper, we propose a method to compute vectors of such unseen words by taking into account the context in which the words have occurred. Next, we also propose a model which utilizes inverse document frequencies (IDF) to efficiently process unseen words by expanding the system's vocabulary. Finally, we validate that the proposed method and model improve the performance of a QA system through experiments.